It takes years of intense study and a steady hand for humans to perform surgery, but it might be easier for robots to grasp it with today’s AI technology.

Researchers at Johns Hopkins University (JHU) and Stanford University have taught a robotic surgical system to perform a host of surgical tasks as capable as human doctors simply by training it on videos of those procedures.

The team benefited from a The da Vinci surgical system for this study. It is a robotic system that is usually controlled remotely by a surgeon with arms that manipulate instruments for tasks such as dissection, suction, and cutting and sealing of vessels. Systems like these give surgeons much more control, precision and a closer look at patients on the operating table. The latest version is estimated cost over $2 millionand that doesn’t include accessories, sterilization equipment or training.

Intuitive

Using a machine learning method known as learning by imitationthe team trained a da Vinci surgical system to perform three tasks involved in surgical procedures on its own: manipulating a needle, lifting body tissue, and suturing. Take a look.

The surgical system not only performed them as well as a human could, but also learned to correct its own mistakes. “If the needle falls, it will automatically pick it up and continue. It’s not something we taught him to do,” said Axel Krieger, an assistant professor at JHU who was a co-author. a paper on the team’s findings that were presented at this week’s Conference on Robot Learning.

The researchers trained an AI model by combining imitation learning with the machine learning architecture that popular chatbots like ChatGPT are built with. However, while these chatbots are designed to work with text, this model spits out kinematics—a language used to describe movement with mathematical elements like numbers and equations—to direct the surgical system’s arms.

Intuitive

The model was trained using hundreds of videos recorded from wrist cameras placed on the da Vinci robot arms during surgical procedures.

The team believes its model could train a robot to perform any type of surgical procedure quickly and much more easily than the traditional method of manually coding each step needed to direct a surgical robot’s actions.

Johns Hopkins University / Stanford University

According to Krieger, this could help make automated surgery a reality sooner than previously thought. “What’s new here is that we just need to collect mocks learning different procedures and we can train a robot to learn it in a few days,” he said. “It allows us to accelerate to the goal of autonomy while reducing medical errors and achieving more precise surgery.”

This could be one of the biggest breakthroughs in the world of robot-assisted surgery in recent years. There are a few automated devices around for use in complex operations such as The CorPath system from Corindus for cardiovascular procedures. However, their capabilities are usually limited to only certain stages of the surgeries they assist with.

Furthermore, Krieger pointed out that coding each step for a robotic system can be excruciatingly slow. “One could spend a decade trying to model the suture,” he said. “And that means suture only for one type of surgery.”

Krieger also previously worked on a different approach to automating surgical tasks. In 2022, his team of researchers developed Smart Tissue autonomous robotor STAR, at JHU. Guided by a structural light-based three-dimensional endoscope and a machine learning-based tracking algorithm, the robot complexly sutured two ends of a pig’s intestine without human intervention.

JHU researchers are now working on training a robot with their imitation learning method to perform a full surgical procedure. It will likely be years before we see robots completely take over for surgeons, but innovations like this could make complex treatments safer and more accessible for patients around the world.

Source: Johns Hopkins University